The Commonplace
Home Three-study pilot Papers Evidence Explore Trends Syntheses Digests References Docs 🎲 Workforce Futures
Direction, evidence grade, and study type are AI-generated labels (gpt-5-mini), not human-verified. Syntheses are LLM-written. "Tensions" are machine-detected candidates, not confirmed contradictions. A research-acceleration tool, not peer review. How this is built →

Coverage quality

A transparent audit of source coverage, PDF status, and whether papers have usable full text, summaries, abstracts, or no usable text.

4057
papers tracked
75.5%
complete full-text coverage
4
suspect full-text records

Text basis

This is the evidence basis available to summarization and synthesis: complete extracted full text when available, otherwise summary or abstract fallbacks.

Text available for papers in the knowledge base.
Text basisPapersShare
Complete full text 3063 75.5%
Suspect or incomplete full text 4 0.1%
Summary only 990 24.4%
Abstract only 0 0.0%
No usable text 0 0.0%

PDF status

PDF lifecycle status for all tracked papers.
StatusPapersShare
Downloaded306775.6%
Paywall65916.2%
Not Found1353.3%
Error1112.7%
Pending852.1%

Source coverage

Source-level paper counts and complete full-text rates.
SourcePapersFull textAssessed
openalex 1892 57.8% 100.0%
arxiv 1816 99.6% 100.0%
semantic_scholar 340 44.4% 100.0%
manual 9 100.0% 100.0%

What counts as full text?

A paper is counted as complete full text only when extracted text is long enough and does not contain known truncation or extraction-error markers. Short, noisy, or marker-laden text is flagged as suspect so it is not treated as reliable full-text coverage.